Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    negative experiences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    million
    -0.07
    反
    -0.07
    .histogram
    -0.06
    乾
    -0.06
     ench
    -0.06
    Used
    -0.06
    Shown
    -0.06
     عليه
    -0.06
    旧
    -0.06
    distributed
    -0.06
    POSITIVE LOGITS
    τίου
    0.07
     віднов
    0.06
    osed
    0.06
    .getHours
    0.06
    loat
    0.06
     nhắc
    0.06
     çevre
    0.06
    oden
    0.06
    (Edit
    0.06
     impacts
    0.06
    Act Density 0.523%

    No Known Activations